© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 45129
    Prev
    Next
    INDEX
    Explanations

    ballistic missiles and armored vehicles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_10_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    k
    1.12
    r
    1.10
    v
    1.05
    et
    1.01
    n
    0.97
    al
    0.97
    m
    0.95
    p
    0.88
    a
    0.85
    in
    0.84
    POSITIVE LOGITS
     ยัง
    0.75
     armored
    0.70
     বিষয়টা
    0.63
    リン
    0.63
     この
    0.63
     コン
    0.62
     ウィ
    0.62
     آن
    0.61
     টাই
    0.61
     മുൻ
    0.61
    Activations Density 0.018%

    No Known Activations